基于鉴别器引导模型的离线模仿学习

Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng, Ming Li, Heming Zhang, Guyue Zhou, Xianyuan Zhan
{"title":"基于鉴别器引导模型的离线模仿学习","authors":"Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng, Ming Li, Heming Zhang, Guyue Zhou, Xianyuan Zhan","doi":"10.48550/arXiv.2207.00244","DOIUrl":null,"url":null,"abstract":"Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations. DMIL adopts a novel cooperative-yet-adversarial learning strategy, which uses the discriminator to guide and couple the learning process of the policy and dynamics model, resulting in improved model performance and robustness. Our framework can also be extended to the case when demonstrations contain a large proportion of suboptimal data. Experimental results show that DMIL and its extension achieve superior performance and robustness compared to state-of-the-art offline IL methods under small datasets.","PeriodicalId":273870,"journal":{"name":"Conference on Robot Learning","volume":"145 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Discriminator-Guided Model-Based Offline Imitation Learning\",\"authors\":\"Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng, Ming Li, Heming Zhang, Guyue Zhou, Xianyuan Zhan\",\"doi\":\"10.48550/arXiv.2207.00244\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations. DMIL adopts a novel cooperative-yet-adversarial learning strategy, which uses the discriminator to guide and couple the learning process of the policy and dynamics model, resulting in improved model performance and robustness. Our framework can also be extended to the case when demonstrations contain a large proportion of suboptimal data. Experimental results show that DMIL and its extension achieve superior performance and robustness compared to state-of-the-art offline IL methods under small datasets.\",\"PeriodicalId\":273870,\"journal\":{\"name\":\"Conference on Robot Learning\",\"volume\":\"145 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Conference on Robot Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2207.00244\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference on Robot Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2207.00244","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

离线模仿学习(IL)是一种无需奖励标签就能从专家演示中解决决策问题的有效方法。现有的离线IL方法在有限的专家数据下存在严重的性能退化问题。包括学习动力学模型可以潜在地提高专家数据的状态-动作空间覆盖率,然而,它也面临着模型近似/泛化误差和推出数据的次优性等挑战性问题。在本文中,我们提出了鉴别器引导的基于模型的离线模仿学习(DMIL)框架,该框架引入了一个鉴别器来同时区分模型推出数据与真实专家演示的动态正确性和次优性。DMIL采用了一种新颖的合作对抗学习策略,利用鉴别器引导和耦合策略和动态模型的学习过程,提高了模型的性能和鲁棒性。我们的框架还可以扩展到演示中包含大量次优数据的情况。实验结果表明,在小数据集下,与目前最先进的离线IL方法相比,dml及其扩展具有更好的性能和鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Discriminator-Guided Model-Based Offline Imitation Learning
Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations. DMIL adopts a novel cooperative-yet-adversarial learning strategy, which uses the discriminator to guide and couple the learning process of the policy and dynamics model, resulting in improved model performance and robustness. Our framework can also be extended to the case when demonstrations contain a large proportion of suboptimal data. Experimental results show that DMIL and its extension achieve superior performance and robustness compared to state-of-the-art offline IL methods under small datasets.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信